Open AccessProceedings Article
Neural Machine Translation by Jointly Learning to Align and Translate
TLDR
It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.Abstract:
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.read more
Citations
More filters
Proceedings ArticleDOI
Deep Communicating Agents for Abstractive Summarization
TL;DR: In this article, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text, connected to a single decoder, trained end-to-end using reinforcement learning.
Proceedings ArticleDOI
A Multiscale Visualization of Attention in the Transformer Model
TL;DR: In this article, an open-source tool that visualizes attention at multiple scales is proposed to detect model bias, locate relevant attention heads, and link neurons to model behavior in the Transformer model.
Posted Content
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
TL;DR: The General Language Understanding Evaluation Benchmark (GLUE) as mentioned in this paper is a tool for evaluating and analyzing the performance of models across a diverse range of existing NLU tasks, which incentivizes sharing knowledge across tasks because some tasks have very limited training data.
Proceedings ArticleDOI
Deterministic non-autoregressive neural sequence modeling by iterative refinement
TL;DR: The proposed conditional non-autoregressive neural sequence model is evaluated on machine translation and image caption generation, and it is observed that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.
Posted Content
Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation.
TL;DR: This work opens a way toward design of even stronger Gaussian Processes, initialization schemes to avoid gradient explosion/vanishing, and deeper understanding of SGD dynamics in modern architectures.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings ArticleDOI
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation
Kyunghyun Cho,Bart van Merriënboer,Caglar Gulcehre,Dzmitry Bahdanau,Fethi Bougares,Holger Schwenk,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +8 more
TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.
Journal ArticleDOI
Learning long-term dependencies with gradient descent is difficult
TL;DR: This work shows why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases, and exposes a trade-off between efficient learning by gradient descent and latching on information for long periods.
Journal ArticleDOI
Bidirectional recurrent neural networks
Mike Schuster,Kuldip K. Paliwal +1 more
TL;DR: It is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution.
Journal ArticleDOI
A neural probabilistic language model
TL;DR: The authors propose to learn a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences, which can be expressed in terms of these representations.